On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

16 results for “Data-aware”

Supervised level-wise pretraining for recurrent neural network initialization in multi-class classificationcs.LG

Proposes a new pretraining strategy for RNNs to improve classification performance.

problem Poor generalization of RNNs due to initial parameter assignment.

method Data-aware layer-wise pretraining strategy to initialize RNN parameters.

result Data-aware strategies positively support the initialization of RNN-based classification models.

Recurrent Neural Networks Classification Initialization Pretraining Data-aware

2019-11-04abs ↗pdf ↗

A Separation Result Between Data-oblivious and Data-aware Poisoning Attackscs.LG

New study shows data-oblivious attacks can outperform data-aware ones.

problem Comparing effectiveness of data-oblivious and data-aware poisoning attacks.

method Theoretical study of feature selection with LASSO, focusing on separation between full-information and oblivious attackers.

result Data-oblivious attacks can achieve the same results as full-information attacks for feature selection with LASSO.

poisoning attacks machine learning feature selection LASSO data-oblivious

2020-03-26abs ↗pdf ↗

Data-Aware and Scalable Sensitivity Analysis for Decision Tree Ensemblescs.LG

New framework detects model weaknesses in decision tree ensembles.

problem Detecting feature sensitivity in decision tree ensembles.

method Data-aware sensitivity framework using MILP and SMT.

result Realistic and interpretable examples of model weaknesses.

Decision Trees Sensitivity Analysis Mixed-Integer Linear Programming Satisfiability Modulo Theories Feature Manipulation

2026-02-07abs ↗pdf ↗

Effective Data-aware Covariance Estimator from Compressed Datacs.LG

DACE estimates covariance from compressed data, improving accuracy.

problem Estimating covariance from large, distributed data.

method Data-aware weighted sampling for unbiased estimation.

result DACE provides more accurate covariance estimation under compression.

covariance estimation compressed data weighted sampling multiclass classification

2020-10-10abs ↗pdf ↗

ADAGIO: Fast Data-aware Near-Isometric Linear Embeddingsstat.ML

Many important applications, including signal reconstruction, parameter estimation, and signal processing in a compressed domain, rely on a low-dimensional representation of the dataset that preserves {\em all} pairwise distances between the data points and leverages the inherent geometric structure that is typically p…

2016-09-17abs ↗pdf ↗

Data-aware customization of activation functions reduces neural network errorcs.LG

Data-aware activation function customization reduces neural network error.

problem Current neural networks lack consideration for specific activation functions.

method Linear algebraic explanation and Diaconis-Shahshahani Approximation Theorem criteria for activation functions.

result Using an even activation function like seagull can reduce neural network error by orders of magnitude.

neural networks activation functions error reduction Diaconis-Shahshahani Approximation Theorem partial exchangeability

2023-01-16abs ↗pdf ↗

Regularising Deep Networks with Deep Generative Modelscs.LG

We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an arbitrary subset of activations conditioned on the remainder. This is a generalisati…

2019-09-25abs ↗pdf ↗

LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instancescs.LG

Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situ…

2017-11-10abs ↗pdf ↗

Sparse sketches with small inversion biascs.DS

A new method reduces the bias in estimating inverse covariance matrices from sketches.

problem Reducing the bias in estimating inverse covariance matrices from sketches.

method Developed a framework for analyzing inversion bias and proposed a new sketching technique called LEverage Score Sparsified (LESS) embeddings.

result The new sketching technique reduces the inversion bias to

O(1/\sqrt d)

for

m=O(d)

, significantly smaller than the

Θ(1)

approximation error.

inversion bias sparse sketches inverse covariance sub-gaussian matrices leverage scores

2020-11-21abs ↗pdf ↗

Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNsstat.ML

Deep neural networks learn by averaging fast variables, revealing a Gaussian process.

problem Analyzing the complex behavior of deep neural networks (DNNs) with billions of parameters.

method Identifying slow variables that average the erratic behavior of fast microscopic variables in fully trained DNNs.

result DNN layers couple only through the second moment (kernels) of their activations and pre-activations, which fluctuate in a nearly Gaussian manner.

deep learning neural networks feature learning Gaussian process thermodynamic theory

2021-12-31abs ↗pdf ↗

Self-Expressive Decompositions for Matrix Approximation and Clusteringcs.IT

Data-aware methods for dimensionality reduction and matrix decomposition aim to find low-dimensional structure in a collection of data. Classical approaches discover such structure by learning a basis that can efficiently express the collection. Recently, "self expression", the idea of using a small subset of data vect…

2015-05-04abs ↗pdf ↗

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformerscs.LG

Our research proves neural collapse in deep ResNets and transformers is globally optimal.

problem Understanding neural collapse in deep learning models.

method Analysis of deep regularized transformers and ResNets trained with cross entropy or mean squared error loss.

result Global optima of deep regularized transformers and ResNets are approximately collapsed, becoming more prominent as depth increases.

neural collapse deep learning residual networks transformers global optimality

2025-05-21abs ↗pdf ↗

Deep differentiable forest with sparse attention for the tabular datacs.LG

A new deep learning model for tabular data improves accuracy over GBDT.

problem Improving accuracy in tabular data classification.

method Differentiable forest with sparse attention mechanism.

result The differentiable forest achieves higher accuracy than GBDT on tabular datasets.

tabular data differentiable forest sparse attention gradient-based optimization binary tree

2020-02-29abs ↗pdf ↗

Continual Density Ratio Estimation in an Online Settingstat.ML

CDRE estimates density ratios in streaming data without historical samples.

problem Online learning with shifting data distributions.

method Iterative estimation of density ratios between initial and current distributions.

result CDRE outperforms standard DRE in estimating divergences between distributions.

density ratio estimation online learning streaming data covariate shift generative models

2021-03-09abs ↗pdf ↗

Scalable Temporal Anomaly Causality Discovery in Large Systems: Achieving Computational Efficiency with Binary Anomaly Flag Datacs.LG

AnomalyCD discovers anomaly causes in large systems with binary flags, reducing computational burden.

problem Learning graphical causal models from large-scale binary anomaly data is computationally expensive.

method AnomalyCD uses anomaly data-aware causality testing, sparse data compression, and edge pruning.

result AnomalyCD reduces computation overhead and improves accuracy on binary anomaly datasets.

anomaly causality binary data graphical causal models large-scale systems computational efficiency

2024-12-16abs ↗pdf ↗

Can Kernel Methods Explain How the Data Affects Neural Collapse?cs.LG

This paper explores how kernel methods can explain data effects on neural collapse.

problem Understanding how data affects neural collapse in neural networks.

method Formulating NC1 as a function of kernel, specializing to NNGP and NTK, and exploring a data-aware Gaussian Process kernel.

result The NTK does not represent more collapsed features than the NNGP for Gaussian data, highlighting the limitations of data-independent kernels.

Neural Collapse Kernel Methods Neural Networks Data Effects Gaussian Process

2024-06-04abs ↗pdf ↗